# DEMON：实时可演奏的扩散音乐引擎

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-27 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmpvhtd13070xsl0zx6q41oxk
- 原文链接：https://arxiv.org/abs/2605.28657

## AI 摘要

DEMON 是一个实时扩散引擎，将扩散去噪过程转化为可实时演奏的乐器。它基于 ACE-Step 1.5 和 StreamDiffusion 的环形缓冲区架构，采用 TensorRT 加速，在单块 RTX 5090 GPU 上可实现每秒 12.3 次解码完成（60秒音乐），在生产环境环深度 4 下达每秒 11.3 次生成。通过四个核心机制——异构去噪调度、共享可变状态、逐帧源混合与窗口化 VAE 解码——实现了参数的低延迟控制与高达 8.0 倍的解码加速。

## 正文

We present DEMON, a real-time diffusion engine that makes the denoising process playable as a live musical instrument: a control surface both broad (many parameters shaped per-frame across the output) and responsive (each control taking effect as fast as its place in the denoising loop allows). Built on ACE-Step 1.5 and StreamDiffusion's ring-buffer architecture with TensorRT acceleration, it sustains up to 12.3 decoder completions per second for 60-second music on a single consumer GPU (RTX 5090), or 11.3 generations per second at our production ring-depth of 4. At these rates denoising parameters become viable as live performance controls, but the ring buffer propagates per-request changes only at its drain rate, a floor of S denoising steps. We contribute four mechanisms. (1) Per-slot heterogeneous denoise scheduling: each ring-buffer slot owns its timestep schedule, so a moving denoise slider is tracked without wiping the in-flight queue, where the upstream global-schedule design must rebuild and discard it. (2) Shared mutable per-step state, giving any parameter consulted at every solver step next-tick effect, bypassing ring-buffer drain. (3) Per-frame source blending: a sampling-time control on the standard SDE re-noise step, giving a framewise transformation-strength axis that complements scalar denoise scheduling. (4) Windowed VAE decode exploiting receptive-field analysis for an 8.0x decode speedup. Together these separate streaming-diffusion parameters into four propagation classes, by onset and convergence latency.